Computer Vision in the Media Field and Its Contribution to Content Creation

Abstract

The integration and development of computer vision and art design in the media field is an important area of ongoing research and exploration in the humanities and society. This paper takes Generative Adversarial Network(GAN) as the research entry point, proposes its specific application in AIGC, and constructs an image art stylization model based on GAN to realize the migration of image art style for content creation in the media field. On this basis, corresponding to the needs of content generation and creation in the media field, the digital media content generation and creation technology based on computer vision technology is proposed to ensure the quality of the generated content. The content generation and creation technology in the media field proposed in this paper is applied to design public art in the public resting area of Guanfeng Village in Ganbei, Jiangxi Province, China, designing a public art gallery and evaluating it in comparison with neighboring villages such as Wangkou Village, Xiaoqi Village, Likeng Village and Huangling Village. Among the 25 adjective pairs in the public semantic evaluation, except for the adjective pair “abstract - figurative”, the value of positive adjective pairs in the remaining adjective pairs of Guanfeng Village is closest to 1, which brings the public a good artistic emotional experience. The value of all the remaining adjective pairs in favor of positive is close to 1.